Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1607 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.6556. Min Act: -0.0001

Data Index: 175764 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.5831. Min Act: -0.0002

Data Index: 937218 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.4795. Min Act: -0.0002

Data Index: 484701 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.3375. Min Act: -0.0001

Data Index: 1070837 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.4626. Min Act: -0.0002

Data Index: 196298 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.3057. Min Act: -0.0001

Data Index: 676407 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.2914. Min Act: -0.0002

Data Index: 148749 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.3623. Min Act: -0.0002

Data Index: 153214 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.3981. Min Act: -0.0001

Data Index: 409708 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.2616. Min Act: -0.0001

Data Index: 721503 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.3167. Min Act: -0.0001

Data Index: 578272 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.2176. Min Act: -0.0001

Data Index: 896874 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.2678. Min Act: -0.0001

Data Index: 1081780 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.1453. Min Act: -0.0001

Data Index: 9231 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.1414. Min Act: -0.0001

Data Index: 920520 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.2479. Min Act: -0.0001

Data Index: 1012753 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.1575. Min Act: -0.0001

Data Index: 666661 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.1974. Min Act: -0.0001

Data Index: 597345 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.1450. Min Act: -0.0002

Data Index: 243366 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 1.6556. Min Range: -1.6556

Max Act: 1.0974. Min Act: -0.0001

Data Index: 16216 (C4 (Web Text))

Max Activating Token Index: 900